Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search

About

Current neural architecture search (NAS) methods are often limited by their predefined, restrictive search spaces. While recent large language model (LLM)-assisted NAS methods enable open-ended search spaces, they often suffer from inefficient exploration due to biased or low-quality design ideas. To address these issues, we propose to semi-automatically structure model design knowledge to guide the search process. Our approach first defines a high-level structural template of architectural attributes. An LLM then populates this template by analyzing papers, creating a rich and diverse search space that embodies this structured design knowledge. To efficiently explore this vast space, we introduce FairNAD, using a multi-type mutation that enables broad exploration through mutation with fair idea sampling, Pareto-aware mutation, LLM-driven iterative mutation, and a fine-grained feedback loop. We demonstrate the effectiveness of FairNAD in discovering high-performing architectures that yield 0.84, 2.17, and 2.35 points improvement on CIFAR-10, CIFAR-100, and ImageNet16-120, respectively, compared to current state-of-the-art methods.

Yuiko Sakuma, Masakazu Yoshimura, Marcel Gr\"opl, Zitang Sun, Junji Otsuka, Atsushi Irie, Takeshi Ohashi• 2026

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-10 NAS-Bench-201 (test)
Accuracy95.46
225
Image ClassificationCIFAR-100 NAS-Bench-201 (test)
Accuracy78.17
198
Image ClassificationCIFAR-10 NAS-Bench-201 (val)
Accuracy92.2
169
Image ClassificationImageNet-16-120 NAS-Bench-201 (test)
Accuracy52.87
167
Image ClassificationCIFAR-100 NAS-Bench-201 (val)
Accuracy78.75
139
Image ClassificationImageNet 16-120 NAS-Bench-201 (val)
Accuracy52.73
123
Showing 6 of 6 rows

Other info

Follow for update